© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49022
    Prev
    Next
    INDEX
    Explanations

    special characters

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ా
    0.44
    sal
    0.43
    sik
    0.41
    েও
    0.40
    ONSE
    0.40
    ։
    0.40
    sou
    0.39
    synchron
    0.39
    iš
    0.38
    aque
    0.38
    POSITIVE LOGITS
    ”
    0.45
    ️
    0.37
    ”!
    0.37
    tona
    0.36
    жуть
    0.35
    фектив
    0.35
    )”
    0.34
    ไหม
    0.34
    त्री
    0.34
    েশন
    0.33
    Activations Density 0.012%

    No Known Activations